Writ Large on Your Face: Observing Emotions Using Automatic Facial Analysis

Emotions affect all of our daily decisions and, of course, they also influence our evaluations of brands, products and advertisements. But what exactly do consumers feel when they watch a TV commercial, visit a website or when they interact with a brand in different ways? Measuring such emotions is...

Full description

Bibliographic Details
Main Authors: Dieckmann Anja, Unfried Matthias
Format: Article
Language:English
Published: Sciendo 2014-05-01
Series:GfK Marketing Intelligence Review
Subjects:
Online Access:http://www.degruyter.com/view/j/gfkmir.2014.6.issue-1/gfkmir-2014-0009/gfkmir-2014-0009.xml?format=INT
Description
Summary:Emotions affect all of our daily decisions and, of course, they also influence our evaluations of brands, products and advertisements. But what exactly do consumers feel when they watch a TV commercial, visit a website or when they interact with a brand in different ways? Measuring such emotions is not an easy task. In the past, the effectiveness of marketing material was evaluated mostly by subsequent surveys. Now, with the emergence of neuroscientific approaches like EEG, the measurement of real-time reactions is possible, for instance, when watching a commercial. However, most neuroscientific procedures are fairly invasive and irritating. For an EEG, for instance, numerous electrodes need to be placed on the participant's scalp. Furthermore, data analysis is highly complex. Scientific expertise is necessary for interpretation, so the procedure remains a black box to most practitioners and the results are still rather controversial. By contrast, automatic facial analysis provides similar information without having to wire study participants. In addition, the results of such analyses are intuitive and easy to interpret even for laypeople. These convincing advantages led GfK Company to decide on facial analysis and to develop a tool suitable for measuring emotional responses to marketing stimuli, making it easily applicable in marketing research practice.
ISSN:1865-5866